1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
use crate::err::ProcessingResult;
use crate::proc::{Checkpoint, Processor, ProcessorRange};
use crate::spec::codepoint::is_whitespace;
use crate::spec::tag::content::CONTENT_TAGS;
use crate::spec::tag::contentfirst::CONTENT_FIRST_TAGS;
use crate::spec::tag::formatting::FORMATTING_TAGS;
use crate::spec::tag::wss::WSS_TAGS;
use crate::unit::bang::process_bang;
use crate::unit::comment::process_comment;
use crate::unit::entity::{EntityType, parse_entity};
use crate::unit::tag::process_tag;

#[derive(Copy, Clone, PartialEq, Eq, Debug)]
enum ContentType {
    Comment,
    Bang,
    OpeningTag,

    Start,
    End,
    Entity,
    Whitespace,
    Text,
}

impl ContentType {
    fn is_comment_bang_opening_tag(&self) -> bool {
        match self {
            ContentType::Comment | ContentType::Bang | ContentType::OpeningTag => true,
            _ => false,
        }
    }

    fn peek(proc: &mut Processor) -> ContentType {
        // TODO Optimise.
        if proc.at_end() || chain!(proc.match_seq(b"</").matched()) {
            return ContentType::End;
        };

        if chain!(proc.match_pred(is_whitespace).matched()) {
            return ContentType::Whitespace;
        };

        if chain!(proc.match_seq(b"<!--").matched()) {
            return ContentType::Comment;
        };

        // Check after comment
        if chain!(proc.match_seq(b"<!").matched()) {
            return ContentType::Bang;
        };

        // Check after comment and bang
        if chain!(proc.match_char(b'<').matched()) {
            return ContentType::OpeningTag;
        };

        if chain!(proc.match_char(b'&').matched()) {
            return ContentType::Entity;
        };

        ContentType::Text
    }
}

pub fn process_content(proc: &mut Processor, parent: Option<ProcessorRange>) -> ProcessingResult<()> {
    let collapse_whitespace = match parent {
        Some(tag_name) => !WSS_TAGS.contains(&proc[tag_name]),
        // Should collapse whitespace for root content.
        None => true,
    };
    let destroy_whole_whitespace = match parent {
        Some(tag_name) => !WSS_TAGS.contains(&proc[tag_name]) && !CONTENT_TAGS.contains(&proc[tag_name]) && !CONTENT_FIRST_TAGS.contains(&proc[tag_name]) && !FORMATTING_TAGS.contains(&proc[tag_name]),
        // Should destroy whole whitespace for root content.
        None => true,
    };
    let trim_whitespace = match parent {
        Some(tag_name) => !WSS_TAGS.contains(&proc[tag_name]) && !FORMATTING_TAGS.contains(&proc[tag_name]),
        // Should trim whitespace for root content.
        None => true,
    };

    let mut last_non_whitespace_content_type = ContentType::Start;
    // Whether or not currently in whitespace.
    let mut whitespace_checkpoint_opt: Option<Checkpoint> = None;
    let mut entity: Option<EntityType> = None;

    loop {
        let next_content_type = match ContentType::peek(proc) {
            ContentType::Entity => {
                // Entity could decode to whitespace.
                entity = Some(parse_entity(proc, false)?);
                let ws = match entity {
                    Some(EntityType::Ascii(c)) => is_whitespace(c),
                    _ => false,
                };
                if ws {
                    // Skip whitespace char, and mark as whitespace.
                    ContentType::Whitespace
                } else {
                    // Not whitespace, but don't write yet until any previously ignored whitespace has been processed later.
                    ContentType::Entity
                }
            }
            ContentType::Whitespace => {
                // Whitespace is always ignored and then processed afterwards, even if not minifying.
                proc.skip_expect();
                ContentType::Whitespace
            }
            other_type => other_type,
        };

        if next_content_type == ContentType::Whitespace {
            match whitespace_checkpoint_opt {
                None => {
                    // This is the start of one or more whitespace characters, so start a view of this contiguous whitespace
                    // and don't write any characters that are part of it yet.
                    whitespace_checkpoint_opt = Some(proc.checkpoint());
                }
                _ => {
                    // This is part of a contiguous whitespace, but not the start of, so simply ignore.
                }
            }
            continue;
        }

        // Next character is not whitespace, so handle any previously ignored whitespace.
        if let Some(ws) = whitespace_checkpoint_opt {
            if destroy_whole_whitespace && last_non_whitespace_content_type.is_comment_bang_opening_tag() && next_content_type.is_comment_bang_opening_tag() {
                // Whitespace is between two tags, comments, or bangs.
                // destroy_whole_whitespace is on, so don't write it.
            } else if trim_whitespace && (next_content_type == ContentType::End || last_non_whitespace_content_type == ContentType::Start) {
                // Whitespace is leading or trailing.
                // should_trim_whitespace is on, so don't write it.
            } else if collapse_whitespace {
                // Current contiguous whitespace needs to be reduced to a single space character.
                proc.write(b' ');
            } else {
                // Whitespace cannot be minified, so write in entirety.
                proc.write_skipped(ws);
            }

            // Reset whitespace buffer.
            whitespace_checkpoint_opt = None;
        };

        // Process and consume next character(s).
        match next_content_type {
            ContentType::Comment => { process_comment(proc)?; }
            ContentType::Bang => { process_bang(proc)?; }
            ContentType::OpeningTag => { process_tag(proc)?; }
            ContentType::End => { break; }
            ContentType::Entity => entity.unwrap().keep(proc),
            ContentType::Text => { proc.accept()?; }
            _ => unreachable!(),
        };

        last_non_whitespace_content_type = next_content_type;
    };

    Ok(())
}